1 files changed, 46 insertions, 3 deletions

diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index a48d7f11c7b..975c963e578 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -1,8 +1,43 @@
 #ifndef __LINUX_UACCESS_H__
 #define __LINUX_UACCESS_H__
 
+#include <linux/preempt.h>
 #include <asm/uaccess.h>
 
+/*
+ * These routines enable/disable the pagefault handler in that
+ * it will not take any locks and go straight to the fixup table.
+ *
+ * They have great resemblance to the preempt_disable/enable calls
+ * and in fact they are identical; this is because currently there is
+ * no other way to make the pagefault handlers do this. So we do
+ * disable preemption but we don't necessarily care about that.
+ */
+static inline void pagefault_disable(void)
+{
+        inc_preempt_count();
+        /*
+         * make sure to have issued the store before a pagefault
+         * can hit.
+         */
+        barrier();
+}
+
+static inline void pagefault_enable(void)
+{
+        /*
+         * make sure to issue those last loads/stores before enabling
+         * the pagefault handler again.
+         */
+        barrier();
+        dec_preempt_count();
+        /*
+         * make sure we do..
+         */
+        barrier();
+        preempt_check_resched();
+}
+
 #ifndef ARCH_HAS_NOCACHE_UACCESS
 
 static inline unsigned long __copy_from_user_inatomic_nocache(void *to,
@@ -30,14 +65,22 @@ static inline unsigned long __copy_from_user_nocache(void *to,
  * do_page_fault() doesn't attempt to take mmap_sem.  This makes
  * probe_kernel_address() suitable for use within regions where the caller
  * already holds mmap_sem, or other locks which nest inside mmap_sem.
+ * This must be a macro because __get_user() needs to know the types of the
+ * args.
+ *
+ * We don't include enough header files to be able to do the set_fs().  We
+ * require that the probe_kernel_address() caller will do that.
  */
 #define probe_kernel_address(addr, retval)              \
         ({                                              \
                 long ret;                               \
+                mm_segment_t old_fs = get_fs();         \
                                                         \
-                inc_preempt_count();                    \
-                ret = __get_user(retval, addr);         \
-                dec_preempt_count();                    \
+                set_fs(KERNEL_DS);                      \
+                pagefault_disable();                    \
+                ret = __get_user(retval, (__force typeof(retval) __user *)(addr));              \
+                pagefault_enable();                     \
+                set_fs(old_fs);                         \
                 ret;                                    \
         })